{"id":"https://openalex.org/W3011026433","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023283","title":"A Prosodic Mandarin Text-to-Speech System Based on Tacotron","display_name":"A Prosodic Mandarin Text-to-Speech System Based on Tacotron","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3011026433","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023283","mag":"3011026433"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023283","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023283","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033714204","display_name":"Chuxiong Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chuxiong Zhang","raw_affiliation_strings":["Data Science Research Center, Duke Kunshan University, China"],"affiliations":[{"raw_affiliation_string":"Data Science Research Center, Duke Kunshan University, China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100394046","display_name":"Sheng Zhang","orcid":"https://orcid.org/0000-0003-1732-0011"},"institutions":[{"id":"https://openalex.org/I4210166603","display_name":"Jinling Institute of Technology","ror":"https://ror.org/05em1gq62","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210166603"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng Zhang","raw_affiliation_strings":["Jiangsu Jinling Science and Technology Group Limited"],"affiliations":[{"raw_affiliation_string":"Jiangsu Jinling Science and Technology Group Limited","institution_ids":["https://openalex.org/I4210166603"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100549737","display_name":"Hai-Bing Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210166603","display_name":"Jinling Institute of Technology","ror":"https://ror.org/05em1gq62","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210166603"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haibing Zhong","raw_affiliation_strings":["Jiangsu Jinling Science and Technology Group Limited"],"affiliations":[{"raw_affiliation_string":"Jiangsu Jinling Science and Technology Group Limited","institution_ids":["https://openalex.org/I4210166603"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5033714204"],"corresponding_institution_ids":["https://openalex.org/I4210159968"],"apc_list":null,"apc_paid":null,"fwci":0.8659,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.81896908,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"abs 1710 7654","issue":null,"first_page":"165","last_page":"169"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.9146380424499512},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.8882949352264404},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.8171352744102478},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7825605869293213},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6576769351959229},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6458594799041748},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.601327657699585},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5746253132820129},{"id":"https://openalex.org/keywords/chinese-speech-synthesis","display_name":"Chinese speech synthesis","score":0.5214706659317017},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.43589192628860474},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.4256115257740021},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4102633595466614},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15939226746559143},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11470577120780945}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.9146380424499512},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8882949352264404},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.8171352744102478},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7825605869293213},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6576769351959229},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6458594799041748},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.601327657699585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5746253132820129},{"id":"https://openalex.org/C73411735","wikidata":"https://www.wikidata.org/wiki/Q16369","display_name":"Chinese speech synthesis","level":4,"score":0.5214706659317017},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.43589192628860474},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.4256115257740021},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4102633595466614},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15939226746559143},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11470577120780945},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/apsipaasc47483.2019.9023283","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023283","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},{"id":"mag:3174328992","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=202002241820367912","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1499332833","https://openalex.org/W1576227399","https://openalex.org/W1599623585","https://openalex.org/W1902237438","https://openalex.org/W1924770834","https://openalex.org/W2030351702","https://openalex.org/W2064675550","https://openalex.org/W2102003408","https://openalex.org/W2133564696","https://openalex.org/W2134973740","https://openalex.org/W2150658333","https://openalex.org/W2152859600","https://openalex.org/W2168274102","https://openalex.org/W2191779130","https://openalex.org/W2294797155","https://openalex.org/W2327501763","https://openalex.org/W2337335398","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2598638573","https://openalex.org/W2745387029","https://openalex.org/W2749609415","https://openalex.org/W2766812927","https://openalex.org/W2794490148","https://openalex.org/W2901997113","https://openalex.org/W2964060510","https://openalex.org/W2964243274","https://openalex.org/W2964301388","https://openalex.org/W4295731579","https://openalex.org/W6623517193","https://openalex.org/W6696843773","https://openalex.org/W6745697700"],"related_works":["https://openalex.org/W3149582125","https://openalex.org/W2349468610","https://openalex.org/W2465421051","https://openalex.org/W2181715843","https://openalex.org/W652196294","https://openalex.org/W2395605663","https://openalex.org/W1984347656","https://openalex.org/W2772686614","https://openalex.org/W4200068392","https://openalex.org/W231741463"],"abstract_inverted_index":{"The":[0],"Tacotron":[1,24,52,81],"performs":[2,107],"well":[3],"in":[4,17,75,96],"English":[5],"speech":[6],"synthesis":[7,57,82,105],"and":[8],"successfully":[9],"aligns":[10],"two":[11],"arbitrary":[12],"sequences":[13],"from":[14,66],"different":[15],"domain":[16],"an":[18],"automatic":[19],"way.":[20],"However,":[21],"to":[22,46],"introduce":[23],"into":[25,51],"Mandarin":[26,55],"Chinese":[27,56],"Text-to-Speech":[28],"(TTS),":[29],"a":[30,43,80],"prosody":[31,60],"system":[32,74,83,106,113,117],"is":[33],"needed":[34],"for":[35,54,118],"generating":[36],"more":[37],"natural":[38],"speech.":[39],"This":[40],"paper":[41],"proposes":[42],"practical":[44],"method":[45],"involve":[47],"the":[48,63,67,72,90,99,104,111,115],"prosodic":[49,64,91,112],"annotation":[50],"training":[53],"system.":[58],"A":[59],"model":[61],"predicting":[62],"boundaries":[65],"given":[68],"text":[69],"serves":[70],"as":[71,114],"front-end":[73,116],"our":[76],"approach,":[77],"followed":[78],"by":[79,109],"trained":[84],"with":[85],"well-labeled":[86],"TTS":[87],"database":[88],"containing":[89],"annotations.":[92],"Under":[93],"subjective":[94],"evaluation":[95],"terms":[97],"of":[98],"prosody,":[100],"results":[101],"show":[102],"that":[103],"better":[108],"adding":[110],"Tacotron.":[119]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}